1 files changed, 148 insertions, 150 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9f72b092bc22..af97ddcc6b3e 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -50,7 +50,6 @@
 				 BTRFS_SUPER_FLAG_METADUMP |\
 				 BTRFS_SUPER_FLAG_METADUMP_V2)
 
-static const struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
@@ -205,53 +204,6 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
 #endif
 
 /*
- * extents on the btree inode are pretty simple, there's one extent
- * that covers the entire device
- */
-struct extent_map *btree_get_extent(struct btrfs_inode *inode,
-				    struct page *page, size_t pg_offset,
-				    u64 start, u64 len)
-{
-	struct extent_map_tree *em_tree = &inode->extent_tree;
-	struct extent_map *em;
-	int ret;
-
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, start, len);
-	if (em) {
-		read_unlock(&em_tree->lock);
-		goto out;
-	}
-	read_unlock(&em_tree->lock);
-
-	em = alloc_extent_map();
-	if (!em) {
-		em = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-	em->start = 0;
-	em->len = (u64)-1;
-	em->block_len = (u64)-1;
-	em->block_start = 0;
-
-	write_lock(&em_tree->lock);
-	ret = add_extent_mapping(em_tree, em, 0);
-	if (ret == -EEXIST) {
-		free_extent_map(em);
-		em = lookup_extent_mapping(em_tree, start, len);
-		if (!em)
-			em = ERR_PTR(-EIO);
-	} else if (ret) {
-		free_extent_map(em);
-		em = ERR_PTR(ret);
-	}
-	write_unlock(&em_tree->lock);
-
-out:
-	return em;
-}
-
-/*
  * Compute the csum of a btree block and store the result to provided buffer.
  */
 static void csum_tree_block(struct extent_buffer *buf, u8 *result)
@@ -545,38 +497,35 @@ static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct page *page)
 static int check_tree_block_fsid(struct extent_buffer *eb)
 {
 	struct btrfs_fs_info *fs_info = eb->fs_info;
-	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs;
 	u8 fsid[BTRFS_FSID_SIZE];
-	int ret = 1;
+	u8 *metadata_uuid;
 
 	read_extent_buffer(eb, fsid, offsetof(struct btrfs_header, fsid),
 			   BTRFS_FSID_SIZE);
-	while (fs_devices) {
-		u8 *metadata_uuid;
+	/*
+	 * Checking the incompat flag is only valid for the current fs. For
+	 * seed devices it's forbidden to have their uuid changed so reading
+	 * ->fsid in this case is fine
+	 */
+	if (btrfs_fs_incompat(fs_info, METADATA_UUID))
+		metadata_uuid = fs_devices->metadata_uuid;
+	else
+		metadata_uuid = fs_devices->fsid;
 
-		/*
-		 * Checking the incompat flag is only valid for the current
-		 * fs. For seed devices it's forbidden to have their uuid
-		 * changed so reading ->fsid in this case is fine
-		 */
-		if (fs_devices == fs_info->fs_devices &&
-		    btrfs_fs_incompat(fs_info, METADATA_UUID))
-			metadata_uuid = fs_devices->metadata_uuid;
-		else
-			metadata_uuid = fs_devices->fsid;
+	if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE))
+		return 0;
 
-		if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE)) {
-			ret = 0;
-			break;
-		}
-		fs_devices = fs_devices->seed;
-	}
-	return ret;
+	list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list)
+		if (!memcmp(fsid, seed_devs->fsid, BTRFS_FSID_SIZE))
+			return 0;
+
+	return 1;
 }
 
-static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
-				      u64 phy_offset, struct page *page,
-				      u64 start, u64 end, int mirror)
+int btrfs_validate_metadata_buffer(struct btrfs_io_bio *io_bio, u64 phy_offset,
+				   struct page *page, u64 start, u64 end,
+				   int mirror)
 {
 	u64 found_start;
 	int found_level;
@@ -864,9 +813,8 @@ static int check_async_write(struct btrfs_fs_info *fs_info,
 	return 1;
 }
 
-static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio,
-					  int mirror_num,
-					  unsigned long bio_flags)
+blk_status_t btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio,
+				       int mirror_num, unsigned long bio_flags)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	int async = check_async_write(fs_info, BTRFS_I(inode));
@@ -951,11 +899,6 @@ static int btree_writepages(struct address_space *mapping,
 	return btree_write_cache_pages(mapping, wbc);
 }
 
-static int btree_readpage(struct file *file, struct page *page)
-{
-	return extent_read_full_page(page, btree_get_extent, 0);
-}
-
 static int btree_releasepage(struct page *page, gfp_t gfp_flags)
 {
 	if (PageWriteback(page) || PageDirty(page))
@@ -995,7 +938,6 @@ static int btree_set_page_dirty(struct page *page)
 }
 
 static const struct address_space_operations btree_aops = {
-	.readpage	= btree_readpage,
 	.writepages	= btree_writepages,
 	.releasepage	= btree_releasepage,
 	.invalidatepage = btree_invalidatepage,
@@ -1208,7 +1150,8 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
 	root->root_key.offset = 0;
 
-	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
+	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0,
+				      BTRFS_NESTING_NORMAL);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
 		leaf = NULL;
@@ -1280,7 +1223,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	 */
 
 	leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
-			NULL, 0, 0, 0);
+			NULL, 0, 0, 0, BTRFS_NESTING_NORMAL);
 	if (IS_ERR(leaf)) {
 		btrfs_put_root(root);
 		return ERR_CAST(leaf);
@@ -1338,32 +1281,26 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
-struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
-					struct btrfs_key *key)
+static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root,
+					      struct btrfs_path *path,
+					      struct btrfs_key *key)
 {
 	struct btrfs_root *root;
 	struct btrfs_fs_info *fs_info = tree_root->fs_info;
-	struct btrfs_path *path;
 	u64 generation;
 	int ret;
 	int level;
 
-	path = btrfs_alloc_path();
-	if (!path)
-		return ERR_PTR(-ENOMEM);
-
 	root = btrfs_alloc_root(fs_info, key->objectid, GFP_NOFS);
-	if (!root) {
-		ret = -ENOMEM;
-		goto alloc_fail;
-	}
+	if (!root)
+		return ERR_PTR(-ENOMEM);
 
 	ret = btrfs_find_root(tree_root, key, path,
 			      &root->root_item, &root->root_key);
 	if (ret) {
 		if (ret > 0)
 			ret = -ENOENT;
-		goto find_fail;
+		goto fail;
 	}
 
 	generation = btrfs_root_generation(&root->root_item);
@@ -1374,21 +1311,31 @@ struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 	if (IS_ERR(root->node)) {
 		ret = PTR_ERR(root->node);
 		root->node = NULL;
-		goto find_fail;
+		goto fail;
 	} else if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
 		ret = -EIO;
-		goto find_fail;
+		goto fail;
 	}
 	root->commit_root = btrfs_root_node(root);
-out:
-	btrfs_free_path(path);
 	return root;
-
-find_fail:
+fail:
 	btrfs_put_root(root);
-alloc_fail:
-	root = ERR_PTR(ret);
-	goto out;
+	return ERR_PTR(ret);
+}
+
+struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
+					struct btrfs_key *key)
+{
+	struct btrfs_root *root;
+	struct btrfs_path *path;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return ERR_PTR(-ENOMEM);
+	root = read_tree_root_path(tree_root, path, key);
+	btrfs_free_path(path);
+
+	return root;
 }
 
 /*
@@ -1476,6 +1423,31 @@ static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
 	return root;
 }
 
+static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info,
+						u64 objectid)
+{
+	if (objectid == BTRFS_ROOT_TREE_OBJECTID)
+		return btrfs_grab_root(fs_info->tree_root);
+	if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
+		return btrfs_grab_root(fs_info->extent_root);
+	if (objectid == BTRFS_CHUNK_TREE_OBJECTID)
+		return btrfs_grab_root(fs_info->chunk_root);
+	if (objectid == BTRFS_DEV_TREE_OBJECTID)
+		return btrfs_grab_root(fs_info->dev_root);
+	if (objectid == BTRFS_CSUM_TREE_OBJECTID)
+		return btrfs_grab_root(fs_info->csum_root);
+	if (objectid == BTRFS_QUOTA_TREE_OBJECTID)
+		return btrfs_grab_root(fs_info->quota_root) ?
+			fs_info->quota_root : ERR_PTR(-ENOENT);
+	if (objectid == BTRFS_UUID_TREE_OBJECTID)
+		return btrfs_grab_root(fs_info->uuid_root) ?
+			fs_info->uuid_root : ERR_PTR(-ENOENT);
+	if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
+		return btrfs_grab_root(fs_info->free_space_root) ?
+			fs_info->free_space_root : ERR_PTR(-ENOENT);
+	return NULL;
+}
+
 int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
 			 struct btrfs_root *root)
 {
@@ -1505,10 +1477,12 @@ void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info)
 	struct btrfs_root *root;
 
 	while (!list_empty(&fs_info->allocated_roots)) {
+		char buf[BTRFS_ROOT_NAME_BUF_LEN];
+
 		root = list_first_entry(&fs_info->allocated_roots,
 					struct btrfs_root, leak_list);
-		btrfs_err(fs_info, "leaked root %llu-%llu refcount %d",
-			  root->root_key.objectid, root->root_key.offset,
+		btrfs_err(fs_info, "leaked root %s refcount %d",
+			  btrfs_root_name(root->root_key.objectid, buf),
 			  refcount_read(&root->refs));
 		while (refcount_read(&root->refs) > 1)
 			btrfs_put_root(root);
@@ -1573,25 +1547,9 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
 	struct btrfs_key key;
 	int ret;
 
-	if (objectid == BTRFS_ROOT_TREE_OBJECTID)
-		return btrfs_grab_root(fs_info->tree_root);
-	if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
-		return btrfs_grab_root(fs_info->extent_root);
-	if (objectid == BTRFS_CHUNK_TREE_OBJECTID)
-		return btrfs_grab_root(fs_info->chunk_root);
-	if (objectid == BTRFS_DEV_TREE_OBJECTID)
-		return btrfs_grab_root(fs_info->dev_root);
-	if (objectid == BTRFS_CSUM_TREE_OBJECTID)
-		return btrfs_grab_root(fs_info->csum_root);
-	if (objectid == BTRFS_QUOTA_TREE_OBJECTID)
-		return btrfs_grab_root(fs_info->quota_root) ?
-			fs_info->quota_root : ERR_PTR(-ENOENT);
-	if (objectid == BTRFS_UUID_TREE_OBJECTID)
-		return btrfs_grab_root(fs_info->uuid_root) ?
-			fs_info->uuid_root : ERR_PTR(-ENOENT);
-	if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
-		return btrfs_grab_root(fs_info->free_space_root) ?
-			fs_info->free_space_root : ERR_PTR(-ENOENT);
+	root = btrfs_get_global_root(fs_info, objectid);
+	if (root)
+		return root;
 again:
 	root = btrfs_lookup_fs_root(fs_info, objectid);
 	if (root) {
@@ -1677,6 +1635,52 @@ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
 }
 
 /*
+ * btrfs_get_fs_root_commit_root - return a root for the given objectid
+ * @fs_info:	the fs_info
+ * @objectid:	the objectid we need to lookup
+ *
+ * This is exclusively used for backref walking, and exists specifically because
+ * of how qgroups does lookups.  Qgroups will do a backref lookup at delayed ref
+ * creation time, which means we may have to read the tree_root in order to look
+ * up a fs root that is not in memory.  If the root is not in memory we will
+ * read the tree root commit root and look up the fs root from there.  This is a
+ * temporary root, it will not be inserted into the radix tree as it doesn't
+ * have the most uptodate information, it'll simply be discarded once the
+ * backref code is finished using the root.
+ */
+struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
+						 struct btrfs_path *path,
+						 u64 objectid)
+{
+	struct btrfs_root *root;
+	struct btrfs_key key;
+
+	ASSERT(path->search_commit_root && path->skip_locking);
+
+	/*
+	 * This can return -ENOENT if we ask for a root that doesn't exist, but
+	 * since this is called via the backref walking code we won't be looking
+	 * up a root that doesn't exist, unless there's corruption.  So if root
+	 * != NULL just return it.
+	 */
+	root = btrfs_get_global_root(fs_info, objectid);
+	if (root)
+		return root;
+
+	root = btrfs_lookup_fs_root(fs_info, objectid);
+	if (root)
+		return root;
+
+	key.objectid = objectid;
+	key.type = BTRFS_ROOT_ITEM_KEY;
+	key.offset = (u64)-1;
+	root = read_tree_root_path(fs_info->tree_root, path, &key);
+	btrfs_release_path(path);
+
+	return root;
+}
+
+/*
  * called by the kthread helper functions to finally call the bio end_io
  * functions.  This is where read checksum verification actually happens
  */
@@ -2115,12 +2119,10 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
 
 	RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
 	extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree,
-			    IO_TREE_INODE_IO, inode);
+			    IO_TREE_BTREE_INODE_IO, inode);
 	BTRFS_I(inode)->io_tree.track_uptodate = false;
 	extent_map_tree_init(&BTRFS_I(inode)->extent_tree);
 
-	BTRFS_I(inode)->io_tree.ops = &btree_extent_io_ops;
-
 	BTRFS_I(inode)->root = btrfs_grab_root(fs_info->tree_root);
 	memset(&BTRFS_I(inode)->location, 0, sizeof(struct btrfs_key));
 	set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);
@@ -2626,18 +2628,17 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 		level = btrfs_super_root_level(sb);
 		tree_root->node = read_tree_block(fs_info, btrfs_super_root(sb),
 						  generation, level, NULL);
-		if (IS_ERR(tree_root->node) ||
-		    !extent_buffer_uptodate(tree_root->node)) {
+		if (IS_ERR(tree_root->node)) {
 			handle_error = true;
+			ret = PTR_ERR(tree_root->node);
+			tree_root->node = NULL;
+			btrfs_warn(fs_info, "couldn't read tree root");
+			continue;
 
-			if (IS_ERR(tree_root->node)) {
-				ret = PTR_ERR(tree_root->node);
-				tree_root->node = NULL;
-			} else if (!extent_buffer_uptodate(tree_root->node)) {
-				ret = -EUCLEAN;
-			}
-
-			btrfs_warn(fs_info, "failed to read tree root");
+		} else if (!extent_buffer_uptodate(tree_root->node)) {
+			handle_error = true;
+			ret = -EIO;
+			btrfs_warn(fs_info, "error while reading tree root");
 			continue;
 		}
 
@@ -2753,7 +2754,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	fs_info->check_integrity_print_mask = 0;
 #endif
 	btrfs_init_balance(fs_info);
-	btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work);
+	btrfs_init_async_reclaim_work(fs_info);
 
 	spin_lock_init(&fs_info->block_group_cache_lock);
 	fs_info->block_group_cache_tree = RB_ROOT;
@@ -2928,7 +2929,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	}
 
 	/*
-	 * Verify the type first, if that or the the checksum value are
+	 * Verify the type first, if that or the checksum value are
 	 * corrupted, we'll find out
 	 */
 	csum_type = btrfs_super_csum_type(disk_super);
@@ -3090,8 +3091,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_sb_buffer;
 	}
 
-	sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
-	sb->s_bdi->ra_pages = VM_READAHEAD_PAGES;
 	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
 	sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE);
 
@@ -3482,8 +3481,12 @@ struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
 		return ERR_CAST(page);
 
 	super = page_address(page);
-	if (btrfs_super_bytenr(super) != bytenr ||
-		    btrfs_super_magic(super) != BTRFS_MAGIC) {
+	if (btrfs_super_magic(super) != BTRFS_MAGIC) {
+		btrfs_release_disk_super(super);
+		return ERR_PTR(-ENODATA);
+	}
+
+	if (btrfs_super_bytenr(super) != bytenr) {
 		btrfs_release_disk_super(super);
 		return ERR_PTR(-EINVAL);
 	}
@@ -4056,6 +4059,7 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	btrfs_cleanup_defrag_inodes(fs_info);
 
 	cancel_work_sync(&fs_info->async_reclaim_work);
+	cancel_work_sync(&fs_info->async_data_reclaim_work);
 
 	/* Cancel or finish ongoing discard work */
 	btrfs_discard_cleanup(fs_info);
@@ -4687,9 +4691,3 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 
 	return 0;
 }
-
-static const struct extent_io_ops btree_extent_io_ops = {
-	/* mandatory callbacks */
-	.submit_bio_hook = btree_submit_bio_hook,
-	.readpage_end_io_hook = btree_readpage_end_io_hook,
-};